content-brief
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill relies on the ubersuggest MCP server hosted at ubersuggest-mcp.neilpatelapi.com, which is an official vendor resource. The tool calls such as keyword_overview and serp_analysis are consistent with the skill's intent to build data-backed content briefs.
- [INDIRECT_PROMPT_INJECTION]: The skill identifies a vulnerability surface for indirect prompt injection by processing external data from the web. 1. Ingestion points: Competitor content and metadata are ingested via serp_analysis and page_keywords tools in SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: The skill is restricted to SEO analysis and outline generation; it lacks the ability to execute shell commands, access the file system, or perform arbitrary network operations. 4. Sanitization: Absent. The impact is assessed as low due to the limited tool capabilities and the requirement for user confirmation for article generation.
Audit Metadata